© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57946
    Prev
    Next
    INDEX
    Explanations

    Telugu-language Pradesh

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åľĪ
    -0.10
    è¡ĮæĶ¿æī§æ³ķ
    -0.09
    æ¹ĸå·ŀ
    -0.09
    Saint
    -0.08
     завиÑģим
    -0.08
    vore
    -0.08
     Blonde
    -0.08
     Tibet
    -0.08
    (mt
    -0.08
    çļĦçľ¼
    -0.08
    POSITIVE LOGITS
    .microsoft
    0.12
    微软
    0.11
     ÑĥкÑĢаин
    0.10
    åĪĺå¤ĩ
    0.10
    ÑĶ
    0.10
    Microsoft
    0.09
    SqlServer
    0.09
     Bail
    0.09
    .azure
    0.09
    .Microsoft
    0.09
    Activations Density 0.251%

    No Known Activations